From 4930f4831b1547b52c5968e9307fe3d840d7fba0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 16 May 2020 10:46:23 +0200 Subject: net: allow __skb_ext_alloc to sleep mptcp calls this from the transmit side, from process context. Allow a sleeping allocation instead of unconditional GFP_ATOMIC. Acked-by: Paolo Abeni Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3000c526f552..531843952809 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4165,7 +4165,7 @@ struct skb_ext { char data[] __aligned(8); }; -struct skb_ext *__skb_ext_alloc(void); +struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); -- cgit From a3fd7ceee05431d2c51ed86c6cae015d236a51f0 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:36 +0200 Subject: net: Introduce netns_bpf for BPF programs attached to netns In order to: (1) attach more than one BPF program type to netns, or (2) support attaching BPF programs to netns with bpf_link, or (3) support multi-prog attach points for netns we will need to keep more state per netns than a single pointer like we have now for BPF flow dissector program. Prepare for the above by extracting netns_bpf that is part of struct net, for storing all state related to BPF programs attached to netns. Turn flow dissector callbacks for querying/attaching/detaching a program into generic ones that operate on netns_bpf. Next patch will move the generic callbacks into their own module. This is similar to how it is organized for cgroup with cgroup_bpf. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Cc: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200531082846.2117903-3-jakub@cloudflare.com --- include/linux/skbuff.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 531843952809..a0d5c2760103 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1283,32 +1283,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); -#ifdef CONFIG_NET -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr); -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog); - -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); -#else -static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) -{ - return -EOPNOTSUPP; -} - -static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) -{ - return -EOPNOTSUPP; -} -#endif - struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); -- cgit From 836e66c218f355ec01ba57671c85abf32961dcea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 2 Jun 2020 16:58:32 +0200 Subject: bpf: Fix up bpf_skb_adjust_room helper's skb csum setting Lorenz recently reported: In our TC classifier cls_redirect [0], we use the following sequence of helper calls to decapsulate a GUE (basically IP + UDP + custom header) encapsulated packet: bpf_skb_adjust_room(skb, -encap_len, BPF_ADJ_ROOM_MAC, BPF_F_ADJ_ROOM_FIXED_GSO) bpf_redirect(skb->ifindex, BPF_F_INGRESS) It seems like some checksums of the inner headers are not validated in this case. For example, a TCP SYN packet with invalid TCP checksum is still accepted by the network stack and elicits a SYN ACK. [...] That is, we receive the following packet from the driver: | ETH | IP | UDP | GUE | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY ip_summed is CHECKSUM_UNNECESSARY because our NICs do rx checksum offloading. On this packet we run skb_adjust_room_mac(-encap_len), and get the following: | ETH | IP | TCP | skb->ip_summed == CHECKSUM_UNNECESSARY Note that ip_summed is still CHECKSUM_UNNECESSARY. After bpf_redirect()'ing into the ingress, we end up in tcp_v4_rcv(). There, skb_checksum_init() is turned into a no-op due to CHECKSUM_UNNECESSARY. The bpf_skb_adjust_room() helper is not aware of protocol specifics. Internally, it handles the CHECKSUM_COMPLETE case via skb_postpull_rcsum(), but that does not cover CHECKSUM_UNNECESSARY. In this case skb->csum_level of the original skb prior to bpf_skb_adjust_room() call was 0, that is, covering UDP. Right now there is no way to adjust the skb->csum_level. NICs that have checksum offload disabled (CHECKSUM_NONE) or that support CHECKSUM_COMPLETE are not affected. Use a safe default for CHECKSUM_UNNECESSARY by resetting to CHECKSUM_NONE and add a flag to the helper called BPF_F_ADJ_ROOM_NO_CSUM_RESET that allows users from opting out. Opting out is useful for the case where we don't remove/add full protocol headers, or for the case where a user wants to adjust the csum level manually e.g. through bpf_csum_level() helper that is added in subsequent patch. The bpf_skb_proto_{4_to_6,6_to_4}() for NAT64/46 translation from the BPF bpf_skb_change_proto() helper uses bpf_skb_net_hdr_{push,pop}() pair internally as well but doesn't change layers, only transitions between v4 to v6 and vice versa, therefore no adoption is required there. [0] https://lore.kernel.org/bpf/20200424185556.7358-1-lmb@cloudflare.com/ Fixes: 2be7e212d541 ("bpf: add bpf_skb_adjust_room helper") Reported-by: Lorenz Bauer Reported-by: Alan Maguire Signed-off-by: Daniel Borkmann Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/CACAyw9-uU_52esMd1JjuA80fRPHJv5vsSg8GnfW3t_qDU4aVKQ@mail.gmail.com/ Link: https://lore.kernel.org/bpf/11a90472e7cce83e76ddbfce81fdfce7bfc68808.1591108731.git.daniel@iogearbox.net --- include/linux/skbuff.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a0d5c2760103..0c0377fc00c2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3919,6 +3919,14 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) } } +static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) +{ + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + skb->ip_summed = CHECKSUM_NONE; + skb->csum_level = 0; + } +} + /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise -- cgit